@inproceedings{77b5ad81ef69496e91340a7dad0d4ae1,
title = "Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers",
abstract = "The project Augmented Multi-party Interaction (AMI) is concerned with the development of meeting browsers and remote meeting assistants for instrumented meeting rooms – and the required component technologies R&D themes: group dynamics, audio, visual, and multimodal processing, content abstraction, and human-computer interaction. The audio-visual processing workpackage within AMI addresses the automatic recognition from audio, video, and combined audio-video streams, that have been recorded during meetings. In this article we describe the progress that has been made in the first two years of the project. We show how the large problem of audio-visual processing in meetings can be split into seven questions, like “Who is acting during the meeting?��?. We then show which algorithms and methods have been developed and evaluated for the automatic answering of these questions.",
keywords = "IR-63415, EC Grant Agreement nr.: FP6/506811, METIS-242051, EWI-6857",
author = "Marc Al-Hamas and Thomas Hain and Jan Cernocky and Sascha Schreiber and Mannes Poel and R.J. Rienks",
note = "10.1007/11965152_3 ; null ; Conference date: 01-05-2006 Through 04-05-2006",
year = "2007",
doi = "10.1007/11965152_3",
language = "Undefined",
isbn = "978-3-540-69267-6",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "24--35",
booktitle = "Proceedings of the 3rd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI 2006)",
address = "Netherlands",
}